Original DALL-E 2 from OpenAI for classic text-to-image generation via the OpenAI Image Generation API. Ready-to-use REST inference API, best performance, no coldstarts, affordable pricing.
Idle
$0.12per run·~83 / $10
ExamplesView all
A calm river winding through a misty forest, oil painting style, soft blending, impressionistic colors, morning light
A cartoon-style tropical fish in an aquarium, vibrant colors and whimsical patterns, oversized expressive eyes, surrounded by colorful coral and bubbles. Soft lighting, square aspect ratio, cheerful and charming mood.
Minimalist style fox with a fluffy tail, standing in an autumn forest.
An orange cat wearing a spacesuit, floating inside a space station, Earth and stars visible in the background, futuristic style, high-resolution rendering
A knight in ancient armor standing on a mountaintop overlooking a battlefield, bathed in sunset light, cinematic lens, shallow depth of field
A vintage steam train passing through autumn mountains, oil painting style, thick brush textures, warm tones, cinematic composition
A woman in a flowing red dress dancing in a field of flowers, oil painting style, dynamic movement, vibrant colors, romantic lighting
A still life of fruit and a glass bottle on a wooden table, oil painting style, textured brushwork, realistic lighting, classical composition
A falcon soaring over a snowy mountain peak, oil painting style, dramatic sky, rich palette, expressive brush strokes.
A cozy cottage by a lake under a starry night sky, oil painting style, reflective water, textured brush strokes, serene mood
Related Models
README
OpenAI DALL-E 2
Create imaginative images from text descriptions with OpenAI's DALL-E 2 — a pioneering text-to-image model known for its artistic versatility and creative interpretation. From oil paintings to digital art, DALL-E 2 transforms your words into visually compelling artwork with distinctive style.
Looking for higher fidelity? Try GPT-Image-1 High Fidelity for maximum quality output.
Why It Looks Great
- Artistic versatility: Excels at various art styles — oil painting, watercolor, impressionism, digital art, and more.
- Creative interpretation: Adds artistic flair and imagination to your descriptions.
- Proven reliability: Battle-tested model with consistent, dependable results.
- Prompt Enhancer: Built-in tool to refine and expand your descriptions automatically.
- Affordable quality: Strong artistic generation at a competitive price point.
Parameters
| Parameter | Required | Description |
|---|---|---|
| prompt | Yes | Text description of the image you want to generate. |
How to Use
- Write your prompt — describe your image with details about subject, style, colors, and mood.
- Use Prompt Enhancer (optional) — click to automatically enrich your description.
- Run — click the button to generate.
- Download — preview and save your generated image.
Pricing
Flat rate per image generation.
| Output | Cost |
|---|---|
| Per image | $0.12 |
Best Use Cases
- Artistic Illustrations — Generate paintings, sketches, and artistic interpretations.
- Creative Exploration — Experiment with visual ideas and artistic directions.
- Concept Visualization — Bring abstract ideas to life with artistic rendering.
- Social Media Content — Create unique, eye-catching visuals for posts.
- Mood Boards & Inspiration — Generate reference imagery for creative projects.
Example Prompts
- "A calm river winding through a misty forest, oil painting style, soft blending, impressionistic colors, morning light"
- "A cozy bookshop interior with warm lighting, watercolor illustration, soft edges"
- "Surreal floating islands with waterfalls, digital art, vibrant fantasy colors"
- "Portrait of a cat wearing a Renaissance collar, classical oil painting style"
- "Abstract geometric cityscape at sunset, art deco poster design"
Pro Tips for Best Results
- Specify the art style explicitly — "oil painting", "watercolor", "impressionistic", "digital art".
- Include color and lighting details — "soft blending", "morning light", "warm tones".
- Describe mood and atmosphere for more evocative results.
- Use the Prompt Enhancer to add artistic terminology to simple ideas.
- DALL-E 2 interprets creatively — embrace the artistic interpretation.
- Combine subject matter with style references for best results.
Notes
- DALL-E 2 is optimized for artistic and creative imagery.
- Processing time is typically fast and consistent.
- For photorealistic needs, consider GPT-Image-1 variants.
Dall E 2 API — Quick start
Grab a WaveSpeedAI API key, then call POST https://api.wavespeed.ai/api/v3/openai/dall-e-2 with your input as JSON. The endpoint returns a prediction id; poll the prediction endpoint until status flips to completed, then read the output URL from data.outputs[0]. Examples for Dall E 2 below.
HTTP example
# Submit the prediction
curl -X POST "https://api.wavespeed.ai/api/v3/openai/dall-e-2" \
-H "Content-Type: application/json" \
-H "Authorization: Bearer $WAVESPEED_API_KEY" \
-d '{
"prompt": "A cinematic shot of a city at sunset, soft golden light",
"enable_base64_output": false
}'
# Response includes a prediction id. Poll for the result:
curl -X GET "https://api.wavespeed.ai/api/v3/predictions/{request_id}/result" \
-H "Authorization: Bearer $WAVESPEED_API_KEY"
# When status is "completed", read the output from data.outputs[0].Node.js example
// npm install wavespeed
const WaveSpeed = require('wavespeed');
const client = new WaveSpeed(); // reads WAVESPEED_API_KEY from env
const result = await client.run("openai/dall-e-2", {
"prompt": "A cinematic shot of a city at sunset, soft golden light",
"enable_base64_output": false
});
console.log(result.outputs[0]); // → URL of the generated outputPython example
# pip install wavespeed
import wavespeed
output = wavespeed.run(
"openai/dall-e-2",
{
"prompt": "A cinematic shot of a city at sunset, soft golden light",
"enable_base64_output": false
}
)
print(output["outputs"][0]) # → URL of the generated outputDall E 2 API — Frequently asked questions
What is the Dall E 2 API?
Dall E 2 is a OpenAI model for image generation, exposed as a REST API on WaveSpeedAI. Original DALL-E 2 from OpenAI for classic text-to-image generation via the OpenAI Image Generation API. Ready-to-use REST inference API, best performance, no coldstarts, affordable pricing. You can call it programmatically or try it from the playground above.
How do I call the Dall E 2 API?
POST your input parameters to the model's REST endpoint (shown in the API tab of this playground) with your WaveSpeedAI API key in the Authorization header. Submission returns a prediction ID; poll the prediction endpoint until status flips to "completed", then read the output URL from the result. The playground generates a ready-to-paste code sample in Python, JavaScript, or cURL for whatever inputs you've set. Full request/response shape is documented at https://wavespeed.ai/docs/docs-api/openai/openai-dall-e-2.
How much does Dall E 2 cost per run?
Dall E 2 starts at $0.12 per run. That figure is the base price — the final charge scales with the parameters you set in the form (output size, length, count, references, or whatever knobs this model exposes), so a higher-quality or larger output costs more than a minimal one. The exact cost for your current input is shown live next to the Generate button before you submit, and the actual per-call charge is recorded on the prediction afterwards.
What inputs does Dall E 2 accept?
Key inputs: `prompt`, `enable_base64_output`. The full JSON schema (types, defaults, allowed values) is rendered above the Generate button and mirrored in the API reference at https://wavespeed.ai/docs/docs-api/openai/openai-dall-e-2.
How long does Dall E 2 take to generate?
Average end-to-end generation time on WaveSpeedAI is around 14 seconds per request — measured across recent runs. Queue time scales with global demand; live status is visible in the prediction record.
Can I use Dall E 2 outputs commercially?
Commercial usage rights depend on the model's license, set by its provider (OpenAI). The license summary appears on the model card above; see WaveSpeedAI's Terms of Service for platform-level conditions.